idk

pipeline/download/test_naptan.py

@@ -89,3 +89,92 @@ def test_deduplicate_naptan_does_not_merge_missing_locality_bus_stops():
     result = deduplicate_naptan(df)
 
     assert len(result) == 2
+
+
+def test_deduplicate_naptan_merges_colocated_missing_locality_bus_stations():
+    # Two NaPTAN records for the same bus station with no locality, co-located
+    # within the merge area, are a true duplicate and collapse to one POI.
+    df = pl.DataFrame(
+        {
+            "id": ["a", "b"],
+            "name": ["Victoria Bus Station", "Victoria Bus Station"],
+            "category": ["Bus station", "Bus station"],
+            "lat": [51.4952, 51.4953],
+            "lng": [-0.1441, -0.1440],
+            "locality": [None, None],
+        }
+    )
+
+    result = deduplicate_naptan(df)
+
+    assert len(result) == 1
+    assert result["name"][0] == "Victoria Bus Station"
+    assert result["category"][0] == "Bus station"
+    assert result["lat"][0] == pytest.approx((51.4952 + 51.4953) / 2)
+
+
+def test_deduplicate_naptan_keeps_rail_station_with_only_station_node():
+    # Aberdare's only NaPTAN record is an RLY station node (StopType "RLY").
+    df = pl.DataFrame(
+        {
+            "id": ["aberdare-rly"],
+            "name": ["Aberdare Rail Station"],
+            "category": ["Rail station"],
+            "lat": [51.7155],
+            "lng": [-3.4438],
+            "locality": ["ABERDARE"],
+            "entrance": [False],
+        }
+    )
+
+    result = deduplicate_naptan(df)
+
+    assert len(result) == 1
+    assert result["name"][0] == "Aberdare Rail Station"
+    assert result["category"][0] == "Rail station"
+
+
+def test_deduplicate_naptan_merges_rail_entrances_into_station_node():
+    # A station node (RLY) and its two entrance nodes (RSE) collapse to a single
+    # "Rail station" POI represented by the station node, not an entrance.
+    df = pl.DataFrame(
+        {
+            "id": ["clapham-rly", "clapham-rse-a", "clapham-rse-b"],
+            "name": [
+                "Clapham Junction Rail Station",
+                "Clapham Junction Rail Station",
+                "Clapham Junction Rail Station",
+            ],
+            "category": ["Rail station", "Rail station", "Rail station"],
+            "lat": [51.4642, 51.4644, 51.4640],
+            "lng": [-0.1705, -0.1702, -0.1708],
+            "locality": ["CLAPHAM", "CLAPHAM", "CLAPHAM"],
+            "entrance": [False, True, True],
+        }
+    )
+
+    result = deduplicate_naptan(df)
+
+    assert len(result) == 1
+    assert result["id"][0] == "clapham-rly"
+    assert result["category"][0] == "Rail station"
+
+
+def test_deduplicate_naptan_does_not_merge_rail_and_ferry_in_same_area():
+    # Different transport modes sharing a name/area stay as separate POIs.
+    df = pl.DataFrame(
+        {
+            "id": ["harbour-rail", "harbour-ferry"],
+            "name": ["Harbour Station", "Harbour Station"],
+            "category": ["Rail station", "Ferry"],
+            "lat": [51.5, 51.5001],
+            "lng": [-0.1, -0.1001],
+            "locality": ["HARBOUR", "HARBOUR"],
+            "entrance": [False, False],
+        }
+    )
+
+    result = deduplicate_naptan(df).sort("category")
+
+    assert len(result) == 2
+    assert result["category"].to_list() == ["Ferry", "Rail station"]